Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive (it does not detect or respond to any content).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pym
    -0.07
     brethren
    -0.07
     iii
    -0.07
    Rem
    -0.07
    elfth
    -0.07
    Jim
    -0.07
    _MESH
    -0.06
     III
    -0.06
     Jim
    -0.06
    Life
    -0.06
    POSITIVE LOGITS
     want
    0.17
     wants
    0.16
     wanted
    0.15
     Want
    0.13
    want
    0.10
     WANT
    0.10
    Want
    0.10
     Wanted
    0.10
     Wants
    0.10
    ant
    0.09
    Act Density 0.085%

    No Known Activations